Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2586 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.7000. Min Range: -4.7000

Max Act: 4.6719. Min Act: -0.1700

Data Index: 2597563 (Open Web Text)

Max Activating Token Index: 462

Text #1

Max Range: 4.7000. Min Range: -4.7000

Max Act: 4.7000. Min Act: -0.1700

Data Index: 4178569 (Open Web Text)

Max Activating Token Index: 358

Text #2

Max Range: 4.7000. Min Range: -4.7000

Max Act: 4.5126. Min Act: -0.1700

Data Index: 1734873 (Open Web Text)

Max Activating Token Index: 673

Text #3

Max Range: 4.7000. Min Range: -4.7000

Max Act: 4.4455. Min Act: -0.1700

Data Index: 460561 (Open Web Text)

Max Activating Token Index: 527

Text #4

Max Range: 4.7000. Min Range: -4.7000

Max Act: 4.4416. Min Act: -0.1700

Data Index: 4167553 (Open Web Text)

Max Activating Token Index: 416

Text #5

Max Range: 4.7000. Min Range: -4.7000

Max Act: 4.3444. Min Act: -0.1700

Data Index: 3068618 (Open Web Text)

Max Activating Token Index: 524

Text #6

Max Range: 4.7000. Min Range: -4.7000

Max Act: 4.3638. Min Act: -0.1700

Data Index: 1731874 (Open Web Text)

Max Activating Token Index: 500

Text #7

Max Range: 4.7000. Min Range: -4.7000

Max Act: 4.3347. Min Act: -0.1700

Data Index: 8555938 (Open Web Text)

Max Activating Token Index: 341

Text #8

Max Range: 4.7000. Min Range: -4.7000

Max Act: 4.3119. Min Act: -0.1700

Data Index: 8691053 (Open Web Text)

Max Activating Token Index: 939

Text #9

Max Range: 4.7000. Min Range: -4.7000

Max Act: 4.3088. Min Act: -0.1700

Data Index: 7335616 (Open Web Text)

Max Activating Token Index: 842

Text #10

Max Range: 4.7000. Min Range: -4.7000

Max Act: 4.3100. Min Act: -0.1700

Data Index: 8414828 (Open Web Text)

Max Activating Token Index: 205

Text #11

Max Range: 4.7000. Min Range: -4.7000

Max Act: 4.2761. Min Act: -0.1700

Data Index: 7343206 (Open Web Text)

Max Activating Token Index: 616

Text #12

Max Range: 4.7000. Min Range: -4.7000

Max Act: 4.2840. Min Act: -0.1700

Data Index: 8062434 (Open Web Text)

Max Activating Token Index: 772

Text #13

Max Range: 4.7000. Min Range: -4.7000

Max Act: 4.2748. Min Act: -0.1700

Data Index: 3184849 (Open Web Text)

Max Activating Token Index: 722

Text #14

Max Range: 4.7000. Min Range: -4.7000

Max Act: 4.2976. Min Act: -0.1700

Data Index: 1544323 (Open Web Text)

Max Activating Token Index: 264

Text #15

Max Range: 4.7000. Min Range: -4.7000

Max Act: 4.3067. Min Act: -0.1700

Data Index: 8359821 (Open Web Text)

Max Activating Token Index: 868

Text #16

Max Range: 4.7000. Min Range: -4.7000

Max Act: 4.3005. Min Act: -0.1700

Data Index: 229065 (Open Web Text)

Max Activating Token Index: 655

Text #17

Max Range: 4.7000. Min Range: -4.7000

Max Act: 4.2466. Min Act: -0.1700

Data Index: 3484851 (Open Web Text)

Max Activating Token Index: 212

Text #18

Max Range: 4.7000. Min Range: -4.7000

Max Act: 4.2627. Min Act: -0.1700

Data Index: 5203928 (Open Web Text)

Max Activating Token Index: 400

Text #19

Max Range: 4.7000. Min Range: -4.7000

Max Act: 4.2889. Min Act: -0.1700

Data Index: 3546869 (Open Web Text)

Max Activating Token Index: 941